This paper addresses the problem of line invariant features matching in a sequence of stereoscopic images of flat objects. The proposed approach is simple, but effective. It is essentially based on the computing of line features which are invariants under the geometrical transformation, such as projective or affine transformation. A line segment is represented by an invariant feature vector in a bi-dimensional parameter space. The line matching is achieved through two processes, the hypothesize and verification process. Each invariant feature vector is directly compared with the pre-registered feature vectors. A pair of lines which are represented by corresponding feature vectors must satisfy some pre-defined geometric constraints (relative angle and distance), in order to be considered matched. Our method is an efficient algorithm which is distinctly fast. Both computer generated and real data are included in experiments to show the stability of the computed features and the convergence speed of the matching system.